Learning from Inconsistencies in an Integrated Cognitive
Architecture
The First Conference on Artificial General Intelligence (AGI-08)
March 1st, 2008
Kai-Uwe Kühnberger (with Peter Geibel, Helmar Gust, Ulf Krumnack, Ekaterina Ovchinnikova, Angela Schwering, Tonio Wandmacher)
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Kai-Uwe Kühnberger et al.
Universität Osnabrück
Overview
Introduction Learning in Cognitive Systems
The I-Cog Architecture General Overview of the System
Learning from Inconsistencies General Remarks Learning from Inconsistencies in Analogy
Making and the Overall System Conclusions
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Introduction
Learning in Cognitive Systems
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Learning
Usually cognitive architectures are based on a number of different modules. Example: Hybrid System
Obviously, coherence problems and consistency clashes can occur, in particular, in hybrid systems.
In hybrid architectures, two main questions can be asked: On which level should learning be implemented? What are plausible strategies in order to resolve
inconsistencies?
Idea of this talk: Use occurring inconsistencies as a mechanism (trigger) of learning.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
The I-Cog Architecture
General Overview
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
A Proposal: I-Cog
I-Cog is a modular system consisting of three main modules: Analogy Engine (AE):
Claim: AE is able to cover a variety of different reasoning abilities.
Ontology Rewriting Device (ORD): Claim: Ontological background knowledge needs to be
implemented in a way, such that dynamic updates are possible. Neuro-Symbolic Learning Device (NSLD):
Claim: The neuro-symbolic learning device enables robust learning of symbolic theories form noisy data.
Finally: these three modules interact in a non-trivial way and are governed by a heuristic-driven Control Device (CD).
Kühnberger, K.-U. et al. (2007): I-Cog: A Computational Framework for Integrated Cognition of Higher Cognitive Abilities, in Proceedings of MICAI 2007, LNAI 4827, pp. 203-214, Springer.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
The Overall I-Cog Architecture
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Learning in I-Cog
Learning is based on occurring inconsistencies In the case of ORD, rewriting algorithms make sure that inconsistencies
are resolved (where this is possible). Ovchinnikova, E. & Kühnberger, K.-U. (2007). Debugging Automatically Extended Ontologies,
GLDV-Journal for Computational Linguistics and Language Technology, 23(2):19-33 .
NSLD is a learning device, where weights are adjusted based on backpropagation of errors.
Gust, H., Kühnberger, K.-U. & Geibel, P. (2007). Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory, in P. Hitzler & B. Hammer (eds.): Perspectives of Neural-Symbolic Integration, Series “Computational Intelligence”, Springer, pp. 209-240.
In the case of AE, it is possible to reduce many adaptation processes to occurring inconsistencies.
Claim 1: Learning is distributed over the whole system. Claim 2: Learning takes place because errors / inconsistencies occur
triggering an adaptation process.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Learning from Inconsistencies
The Example of Analogical Reasoning
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
General Remarks
Inconsistencies are classically connected to logic If for a set of axioms (relative to a language L) can be
entailed and can be entailed, then is inconsistent. We use the term “inconsistency” rather loosely and do not restrict
this concept to logic. Here are some examples: Every analogy establishes a relation that resolves a clash of
concepts, information, interpretations etc. Gust, H. & Kühnberger, K.-U. (2006). Explaining Effective Learning by Analogical Reasoning, 28th
Annual Conference of the Cognitive Science Society, pp. 1417-1422.
Ontology generation / learning Ovchinnikova, E., Wandmacher, T. & Kühnberger, K.-U. (2007). Solving Terminological
Inconsistency Problems in Ontology Design, IBIS 4:65-80.
Non-monotonicity effects in reasoning. Ovchinnikova, E. & Kühnberger, K.-U. (2006). Adaptive ALE-TBox for Extending Terminological
Knowledge, in Proceedings of AI’06, LNAI 4304, Springer, pp. 1111-1115.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
The Analogy Engine
The Analogy Engine is based on Heuristic-Driven Theory Projection (HDTP). HDTP is a mathematically sound theory of computing analogies. It is based on anti-unification of a source theory ThS and a target
theory ThT. It was applied to various domains like naïve physics, metaphors,
geometric figures etc. Some features:
Complex formulas can be anti-unified. A theorem prover allows the re-representation of formulas. Whole theories can be generalized. The involved processes are governed by heuristics.
Gust, H., Kühnberger, K.-U. & Schmid, U. (2006). Metaphors and Heuristic-Driven Theory Projection (HDTP), Theoretical Computer Science, 354:98-117.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Recursion Example I
Source ThS: Addition Target ThT: Multiplication
1: x: add(x,0) = x
2: xy: add(x,s(y)) = s(add(x,y))
1: x: mult(x,s(0)) = x
2: xy: mult(x,s(y)) = add(x,mult(x,y))
Generalized Theory ThG:
1: x: OP1(x,E) = x
2: xy: Op1(x,s(y)) = Op2(Op1(x,y))
For the generalized theory, the following substitutions need to be established:
1: E 0, Op1 add, Op2 s
2: E s(0), Op1 mult, Op2 z.add(x,z)
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Recursion Example II
Source ThS: Addition Target ThT: Multiplication
1: x: add(0,x) = x
2: xy: add(s(y),x) = add(y,s(x))
1: x: mult(0,x) = 0
2: xy: mult(s(y),x) = add(x,mult(x,y))
Generalized Theory ThG:
1: x: Op(E,x) = x
Trying to anti-unify 1 and 1 is not possible. But by using axioms 1 and 2 we can derive
mult(s(0),x) = add(x,mult(0,x)) = add(x,0) = … = add(0,x)Hence we can derive: 3: x: mult(s(0),x) = x For the generalized theory, the following substitutions can be established:
1: E 0, Op add and 2: E s(0), Op mult
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Conclusion
Main claims: In cognitive architectures “inconsistencies” (as
used in the broad sense here) should be considered as a trigger for learning and adaptation.
These adaptation processes can be relevant for: Adapting background knowledge, Reasoning processes of various types, Neuro-based learning approaches.
Learning in the systems is therefore distributed and continuously realized.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Thank you very much!!
Questions?
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
References
Analogical Reasoning (Selection) Gust, H., Kühnberger, K.-U. & Schmid, U. (2006). Metaphors and Heuristic-
Driven Theory Projection (HDTP), Theoretical Computer Science, 354:98-117.
Gust, H. & Kühnberger, K.-U. (2006). Explaining Effective Learning by Analogical Reasoning, in: R. Sun & N. Miyake (eds.): 28th Annual Conference of the Cognitive Science Society, Lawrence Erlbaum, pp. 1417-1422.
Gust, H., Krumnack, U., Kühnberger, K.-U. & Schwering, A. (2007). An Approach to the Semantics of Analogical Relations, in S. Vosniadou et al. (eds.): Proceedings of EuroCogSci 2007, Lawrence Erlbaum, pp. 640-645.
Krumnack, U., Schwering, A., Gust, H. & Kühnberger, K.-U. (2007). Restricted Higher-Order Anti-Unification for Analogy Making, to appear in Proceedings of AI’07, Springer.
Gust, H., Krumnack, U., Kühnberger, K.-U. & Schwering, A. (2008). Analogical Reasoning: A Core of Cognition, to appear in Künstliche Intelligenz 1/2008.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
References
Neuro-Symbolic Integration (Selection) Gust, H., Kühnberger, K.-U. & Geibel, P. (2007). Learning and Memorizing Models
of Logical Theories in a Hybrid Learning Device, to appear in Proceedings of ICONIP 2007, Springer.
Gust, H., Kühnberger, K.-U. & Geibel, P. (2007). Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory, in P. Hitzler & B. Hammer (eds.): Perspectives of Neural-Symbolic Integration, Series “Computational Intelligence”, Springer, pp. 209-240.
Ontology Rewriting (Selection) Ovchinnikova, E. & Kühnberger, K.-U. (2007). Debugging Automatically Extended
Ontologies, GLDV-Journal for Computational Linguistics and Language Technology, volume 23(2).
Ovchinnikova, E., Wandmacher, T. & Kühnberger, K.-U. (2007). Solving Terminological Inconsistency Problems in Ontology Design, International Journal of Interoperability in Business Information Systems, 4:65-80.
Ovchinnikova, E. & Kühnberger, K.-U. (2006). Adaptive ALE-TBox for Extending Terminological Knowledge, in A. Sattar & B. H. Kang (eds.): Proceedings of AI’06, LNAI 4304, Springer, pp. 1111-1115.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
References
I-Cog Kühnberger, K.-U., Geibel, P., Gust, H., Krumnack, U., Ovchinnikova, E.,
Schwering, A. & Wandmacher, T. (2008): Learning from Inconsistencies in an Integrated Cognitive Architecture, to appear in Proceedings of AGI 2008, IOS Press.
Kühnberger, K.-U. (2007): Principles for the Foundation of Integrated Higher Cognition (Abstract). In: D. S. McNamara & J. G. Trafton (Eds.), Proceedings of the CogSci 2007, (p. 1796). Austin, TX: Cognitive Science Society.
Kühnberger, K.-U., Wandmacher T., Schwering, A., Ovchinnikova, E., Krumnack, U., Gust, H. & Geibel, P. (2007): I-Cog: A Computational Framework for Integrated Cognition of Higher Cognitive Abilities, in Proceedings of MICAI 2007, LNAI 4827, pp. 203-214, Springer.
Kühnberger, K.-U., Wandmacher, T., Schwering, A., Ovchinnikova, E., Krumnack, U., Gust, H. & Geibel, P. (2007): Modeling Human-Level Intelligence by Integrated Cognition in a Hybrid Architecture, in P. Hitzler, T. Roth-Berghofer, S. Rudolph: FAInt-07, Workshop at KI 2007, CEUR-WS, vol. 277, pp. 1-15.
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Members of the AI group
Peter Geibel
Karl Gerhards
Helmar Gust
Ulf Krumnack
Kai-Uwe Kühnberger
Jens Michaelis
Ekaterina Ovchinnikova
Angela Schwering
Konstantin Todorov Ulas Türkmen
Tonio Wandmacher
Kai-Uwe Kühnberger et al.
Universität Osnabrück
The First Conference on Artificial General Intelligence (AGI-08)
Memphis, March 1st, 2008
Top Related